Fast, Efficient and Flexible Particle Accelerator Optimisation Using Densely Connected and Invertible Neural Networks
Fast, Efficient and Flexible Particle Accelerator Optimisation Using Densely Connected and Invertible Neural Networks
复制标题
使用密集连接和可逆神经网络进行快速、高效和灵活的粒子加速器优化
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
A. Adelmann
中科院分区：
文献类型：
--
作者：
Renato Bellotti;R. Boiger;A. Adelmann
粒子加速器是在各个学科中进行科学探索和发现的工具。然而，由于涉及大量参数和潜在的非线性动力学，为这些复杂的机器找到优化的操作点是一项具有挑战性的任务。在这里，我们介绍了两类数据驱动的代理模型，它们基于深度和可逆的神经网络，可以取代昂贵的物理计算机模型。这些模型采用多目标优化，找到帕累托最优操作点两个根本不同类型的粒子加速器。我们的方法将多目标加速器优化的解决方案的时间减少到640倍，计算成本高达98%。这里建立的框架应该为粒子加速器的未来在线和实时多目标优化铺平道路。
Particle accelerators are enabling tools for scientific exploration and discovery in various disciplines. However, finding optimised operation points for these complex machines is a challenging task due to the large number of parameters involved and the underlying non-linear dynamics. Here, we introduce two families of data-driven surrogate models, based on deep and invertible neural networks, that can replace the expensive physics computer models. These models are employed in multi-objective optimisations to find Pareto optimal operation points for two fundamentally different types of particle accelerators. Our approach reduces the time-to-solution for a multi-objective accelerator optimisation up to a factor of 640 and the computational cost up to 98%. The framework established here should pave the way for future online and real-time multi-objective optimisation of particle accelerators.